See discussions, stats, and author profiles for this publication at: https://www.researchgate.

net/publication/369475337

LEARNING ANALYTICS AND ITS BENEFIT FOR EDUCATIONAL PURPOSES

Article · March 2023

CITATIONS READS
0 35

3 authors, including:

Rebecca Oluwayimika Kasumu

University of Port Harcourt
35 PUBLICATIONS   49 CITATIONS   

SEE PROFILE

All content following this page was uploaded by Rebecca Oluwayimika Kasumu on 23 March 2023.

The user has requested enhancement of the downloaded file.

GSJ: Volume 10, Issue 4, April 2022
ISSN 2320-9186 2300

GSJ: Volume 10, Issue 4, April 2022, Online: ISSN 2320-9186

www.globalscientificjournal.com
LEARNING ANALYTICS AND ITS BENEFIT FOR EDUCATIONAL PURPOSES

By

Kasumu, Rebecca Oluwayimika

&
Idoghor, Uduak
Department of Curriculum Studies/Educational Technology
Faculty of Education
University of Port Harcourt
yinkabecky1@gmail.com
07033592102

GSJ© 2022
www.globalscientificjournal.com
GSJ: Volume 10, Issue 4, April 2022
ISSN 2320-9186 2301

Introduction

All learning tasks are based on one-way or two-way communication activities, where learners
liaise with their instructors, other learners and content within their learning surroundings. The
appraisal of the success of such interaction is the key point in any learning process since it has
direct impact on learning end product. To put it simply; for assessment motive, administrators and
educators can evaluate the recorded logs of the learning management systems for different types
of data such as the number of logins, documents accesses, reports on achievement etc.

Therefore, the purpose of using recorded data for assessing the effectiveness of teaching-learning
process and using the end product for development and enhancing quality lead to the exposure of
the field known as “learning analytics”. Based on the analysis of data, attainable forecast could be
reached to make suggestions, and give decisions in order to device involvement for the
enhancement of the quality of the process. Hence, the concept of “learning analytics” is a
promising and important field of study with its processes and potential to advance e-learning.

The concept of “learning analytics” is also the interchange of technical and social sides of learning
process (Siemens & Gasevic, 2012). From a technical point of view, the algorithms that forms
predictive systems, personalization models, semantics and network analysis needs deep technical
expertise (Gulbahar & Ilgaz, 2014). From a social point of view, these algorithms are either based
on existing learning theories both individually or socially, or creates new methods to be used for
future applications to improve quality in teaching, based on the research with mining of relevant
data. As a result, being an interdisciplinary area, “learning analytics” promises so much to close
the gaps that exist in communication processes for online communities.

Literature Review

According to Elias (2013), learning analytics is an arising field in which refined analytic tools are
used to improve learning and education. Besides, this field is closely attached to some other fields
like business intelligence, web analytics, academic analytics, educational data mining, and action
analytics. From a learning point of view, where administrators, decision-makers, educators,
teaching staff and learners can benefit from learning analytics, curriculum can benefit from

GSJ© 2022
www.globalscientificjournal.com
GSJ: Volume 10, Issue 4, April 2022
ISSN 2320-9186 2302

learning analytics, curriculum can be upgraded through the use of data for course or program
improvement, whereas learners’ performance can be trailed and enhanced through suitable
interventions based on learning goals, resources and methods for individual purposes (Long &
Siemens, 2013). Furthermore, for institutional advancement, data about learner description and
performance of academics can be used to predict useful models for learner’s academic successes
or failures, and together with some possible national comparisons, necessary interventions for the
institution may become obvious.

Generally, educators can access information to find answers to questions of what and when about
learners, but explaining this information to answer the questions of how and why is still difficult
to some extent. Regarding this issue, Philips, Maor, Cumming-Potvin, Roberts, Herrington,
Preston and Moore (2011) conducted a study and examined students’ access to explore study
characteristics. Realizing that a surface analysis using learning analytics was inadequate to decide
about the experiences, they used the qualitative research method for reaching in-depth data. The
researchers also impart suggestions for expanding and strengthening research about using learning
analytics. Teachers can benefit from information both for themselves and their students in order to
make a more informed judgement. Another option may be to intelligently process data in order to
automatically forecast support guidance. As a teacher, using a learning and/or content management
system as a supplement to a traditional course or for a fully online course, one can get recorded
system information about the activities of the students on a course. By this way, the teacher can
comprehend about the engagement of students into teaching and learning activities (discussion
forums, chats, web links, homework and quizzes), and about the quality and quantity of students’
learning experiences. By examining the data, the teacher not only gains understanding about each
learner in the class, but also has possibility to examine instructional resources, learning activities,
learning processes and the expected outcomes and products. As a learner, the system can recognize
the choice(s) of the learner in terms of his/her learning style or study habits, and provide suitable
guidance to the learners. The learner could be supplied with some self-evaluation materials where
some guidance towards topics that needs further study is also delivered formed on the achievement
of the learner. Moreover, the use of semantic web or social network analysis may also provide
recommendations to the learner about close contents or the resources most preferred by his/her
colleagues.

GSJ© 2022
www.globalscientificjournal.com
GSJ: Volume 10, Issue 4, April 2022
ISSN 2320-9186 2303

Bichsel (2013) probed the present day advantage of using analytics in higher education. It was
found that data is mainly used for keeping track of enrolment management, finance and budgeting,
and student advancement. Parallel with this use, the crucial perceived advantage established on
forecast from the data were describe as understanding student demographics and behaviors,
optimizing the use of resources, engage behaviors, optimizing the use of resources, engage
students and assisting students learn more conclusively. In the same report, reduced, misapplied
of data, rules viewing the use of data and lack of knowledge about the use of data in making
decisions are stated as treat about the development use of analytics in higher education. Bichsel
(2013) also investigated as a key discovery that institutions, which are more active in the process
of investment, cultural change, reporting tools, expertise and infrastructure, are awaited to use data
to make predictions or projections in various areas.

Likewise, Brown (2013) attempted to provide some empirical approach established on concepts.
The researcher mostly emphasized on student advancement and underlined the importance of data
that should be used as predictors and indicators of student advancement. Brown (2013) firstly,
mentioned learning factors like age, gender, ethnicity, current grade point average (GPA) and
previous learning practices that occurs before the course begins and offer some sign of how a
student is willing to prepare for their own learning process. After that, activity and performance
indictors like the number and amount of learning management system logins, the amount of time
spent on the course website, the number of discussion forum messages, grades, and formative quiz
scores, were mentioned by the researcher as these measures are digital fingerprints of learners as
they proceed through the learning process.

Learning analytics unite expertise from different academic disciplines such as educational data
mining and predictive modelling. Academic analytics is now considered as being more agitated
with points of institutional business such as recruitment, and less associated to instruction itself.
The society for learning analytics research (SoLAR) was established in 2013 and adopted as the
most often-quoted definition of learning analytics:

“Learning analytics is the measurement, collection, analysis and reporting of data about
learners and their contexts, for purposes of understanding and optimizing learning and
the environments in which it occurs (Siemens & Gasevic, 2012).”

GSJ© 2022
www.globalscientificjournal.com
GSJ: Volume 10, Issue 4, April 2022
ISSN 2320-9186 2304

Learning analytics is an educational application of web analytics, a science that is commonly used
by businesses to analyze commercial activities, identify spending trends, and predict consumer
behavior. Education is embarking on a similar pursuit into data science with the aim of learner
profiling, a process of gathering and analyzing large amounts of detail about individual student
interactions in online learning activities. The goal is to build better pedagogies, empower students
to take an active part in learning, target at-risk student’s population, and assess factors affecting
completion and student’s success. For learners, educators, and researchers, learning analytics is
already starting to provide crucial insights into student’s progress and interaction with online texts,
courseware, and learning environments used to deliver instruction. Students are beginning to
experience the benefits of learning analytics as they engage with mobile and online platforms that
track data to create responsive, personalized learning experiences.

Aim and Objectives

The study is to examine learning analytics and its benefits for educational purposes. Specifically,
the study intends to:

1. Explain the concept and benefits of learning analytics

2. Describe the framework of learning analytics
3. Examine the levels of learning analytics

Discussion

Concept and benefits of Learning Analytics

Learning analytics can be powerful in giving meaning to interactions and actions in a learning
environment, allowing one to eventually personalize every learning environment based on the
student’s preference and progress. It will also help teachers predict student’s satisfaction before
the class is over. A major aspect of Instructional design and e-Learning development is to know
the behavior of one’s learner. Learning analytics are in essence, the collection of data that is
gathered while learners are engaging in the e-Learning experience. Analytics also consist of the
analysis and reporting of Information. Specifically, concerning e-Learning, vital pieces of data are
recorded throughout the duration of the e-Learning course such as learners’ score on a particular

GSJ© 2022
www.globalscientificjournal.com
GSJ: Volume 10, Issue 4, April 2022
ISSN 2320-9186 2305

test/exam, how quickly they are progressing through a module, how many times have they have
logged in, whether they have participated in a discussion board. At the same time, Learning
Analytics also offer online facilitators and instructors a comprehensive look at how a learner is
performing, if he/she may need additional help with a particular lesson or subject, and even if the
learner is likely to pass or not an e-Learning course. Such data can then be used to make
educational analysis and predictions that help to determine which learning materials are
appropriate, useful or irrelevant for the learners. This is primarily based upon learner’s
performance, skill level, and personal interests.

Learning analytics hold the promise of improving learning efficiency and effectiveness in primary,
secondary, and post- secondary education. Learning analytics are directed towards providing
educators, learners, and administrators with actionable insight to classroom and course level
activities.

The benefits of learning analytics in Education include:

1.Through careful analysis of big data, researchers can determine useful information that can
benefit educational institutions, students, instructors, and researchers in various ways. These
stakeholder benefits include targeted course offerings, curriculum development, student learning
outcomes and behavior, personalized learning, improved instructor performance, post-educational
employment opportunities, and improved research in the field of education.

2.Identifying target courses: An initial benefit that evolves from using big data analysis in
education is the ability of educational institutions to identify targeted courses that more closely
align with student needs and preferences for their program of study. By examining trends in student
enrollment and interests in various disciplines, institutions can focus educational and teaching
resources in programs that maximize student enrollment in the most needed areas of study. Schools
can better predict graduate numbers for long-term planning of enrollment (Althubaiti & Alkhazim,
2014).
3.Curriculum improvement: Using big data allows instructors to make changes and adjustments to
improve curriculum development in the educational system, such as in the use of curricular
mapping of data (Armayor & Leonard, 2010). Through the analysis of big data, educators can
determine weaknesses in student learning and comprehension to determine whether or not

GSJ© 2022
www.globalscientificjournal.com
GSJ: Volume 10, Issue 4, April 2022
ISSN 2320-9186 2306

improvements to the curriculum may prove necessary. Instructors can engage in educational
strategic planning to ensure that the learning curriculum targets student needs to maximize learning
potential.
a. Student learning outcome, behavior, and process: Another key benefit of big data and text
mining focuses on the ability of schools and instructors to determine student learning outcomes in
the educational process as well as determine how to improve student performance. Researchers
noted that the use of educational data mining contributed to positive results in the learning process
(AlShammari, Aldhafiri, & Al-Shammari, 2013). Analysis of the data can help educators
understand the student learning experience through learner interactions with technology tools such
as eLearning and mobile learning. Use of big data also reveals learning behavior, the impact on
adaptive learning, and level of persistence (DiCerbo, 2014) in the learning process.
b. Personalized learning: Using learning analytics, the concept of personalized learning
reveals student success. Dietz-Uhler and Hurn (2013) asserted that course designers do not
account for students who do not begin specific coursework at the same learning stage and
who do not proceed, learn, and master course competencies at the same pace. Learning
analytics allows faculty to use data collected by the learning management system to
observe the frequency of student login. Instructors can also see student interaction within
the course, total engagement, pace, and grades. These components serve as predictors of
students’ potential success or failure. Learning analytics allows for real-time reception of
the pertinent data, review as well as the incorporation of data, and real-time feedback for
every student.
c. Post-educational employment: Using big data allows educational institutions to identify
post education employment opportunities for graduates and help target education that more
closely aligns with employment market needs. It can also predict graduate employment,
unemployment, or undetermined situations about job opportunities (Jantawan & Tsai,
2013). Using big data can help stakeholders in the educational system better understand
vocational prospects for students and better assess student learning programs for
occupational compatibility. In a global learning environment, this type of information not
only can facilitate better educational and post education vocational planning, but also may
prove useful to organizations as they make hiring and budgeting decisions for college
graduates in different disciplines.

GSJ© 2022
www.globalscientificjournal.com
GSJ: Volume 10, Issue 4, April 2022
ISSN 2320-9186 2307

Learning analytics help to improve e-Learning:

1. Helps to predict learners’ performance
2. Provides learners with a personalized e-Learning experience
3. Increased learners’ retention rates
4. Helps to improve future e-Learning courses
5. Boost in cost efficiency (Pappas, 2014).

Learning analytics in many respects, have the ability to change the world of e-Learning whether
in educational institutions or in corporate training. With the data collected through analytics,
instructional designers and e-Learning professionals can offer learners the one key thing that all e-
Learning courses and training modules strive to offer (Pappas, 2014).

Framework for Learning Analytics

What is analytics all about?

Fig 1.1

Source: Long and Siemen (2013)

Educational data mining is concentrated primarily on the complex problems of removing merit
from learning-related big data. Learning analytics is anxious with increasing aspects of learning,
while academic analytics concentrated further on utilizing data for marketing and administrative

GSJ© 2022
www.globalscientificjournal.com
GSJ: Volume 10, Issue 4, April 2022
ISSN 2320-9186 2308

purposes (Long & Siemens, 2013). The collection, analysis and reporting of big data on students
to predict students’ retention, understand learning behaviors, and improve learning through
conditioning than individualized assessment and assistance is introduced to as learning analytics
(Siemens, 2013). The use of learning analytics for predictive reasons is extended to expand to
university and system wide projects (Heath and Leinonen, 2016). Nevertheless, at the present-day
the application of big data to learning analytics for the motives of learning pedagogy is less
common (Dede, Ho, & Mitros, 2016), usually demanding small-scale projects with an emphasis
on apprehending learning and teaching ways (Siemens, Dawson & Lynch., 2013). The uneven
focus on forecast over learning focus the breach between the use of big data and learning analytics
for prediction and its usage to intensify instruction (Dede et al., 2016). As argued by Dede et al.
(2016), the basis for learning analytics should be the effect on student learning, with research
needed into how teachers and students could use learning analytic tools to improve learning. In
order to evolve instrument to ease student learning, an essential first step is to understand students’
approach towards and concern about learning analytics.

According to Andrew, Barbara and Marie (2018), framework within learning analytics include:

1. Descriptive Analytics: it takes the student’s past and aims to analyze the student data to
find patterns in the student’s learning progress. Descriptive analytics describe what has
happened and the way things are, allowing the researcher to make strategic decision on the
best teaching styles for each student. This can be done using a Learning Management
System that a teacher can build the tool.
2. Predictive Analytics: It offers insight into future trends in students’ understanding of the
material. Predictive analytics uses the student’s past data and current data to determine
what is likely to happen next. This can identify students who may soon be low performing
or low engaging. This can allow the teacher help at- risk students get back on track.
3. Prescriptive Analytics: This not only provides teachers with data that can be used to make
actionable decisions, but it provides alternative suggestions to make teaching more
effective. Based on the student data collected, the analytics tool generates suggestions on
different educational resources and tools to utilize in order to make greater impact on
students.

GSJ© 2022
www.globalscientificjournal.com
GSJ: Volume 10, Issue 4, April 2022
ISSN 2320-9186 2309

Teachers can use standardized data to assess instructional decision making and can also use
different form of instruction for different students (Dunn, Ariola, Lo, & Garrison, 2013).

The Open learning initiative for example, depicted multiple uses of micro learning data from online
systems. The open learning initiative developed learning systems for colleges courses such as
Statistics, Biology and Physics. Open learning initiative researchers explained how the data
gathered automatically as students’ interactions with their learning software could be useful not
only for delivery measures of students’ performance but also for informing improvements to the
learning software, providing feedback to instructors teaching a class using a software, and
exploring basic questions about how people learn (Andrew, Barbara & Maria, 2018).

Levels of Learning Analytics

Since learning analytics covers a wide range of analytics, Simon and Timothy (2018) discussed
the three levels of Macro, Meso and Micro of learning analytics as follows:

1. Macro-Level: This enables analytics within the cross-institutional level, and can become more
increasingly real-time and involves more fine data from the Meso and Micro levels. It is also
important to note that at the macro level, learning analytics can be incorporated in non-educational
sectors such as the government sectors. Macro-level analytics seek to enable cross institutional
analytics, for instance, through maturity surveys of current institutional practice or improve state
wide data access to standardized assessment data over students’ lifetimes. Macro-analytics will
become increasingly real-time, incorporating more data from the finer granularity Meso/Micro
levels, and could conceivably benefit from benchmarking and data integration methodologies
developed in non-educational sectors.

2. Meso-Level: This enables analytics at the institutional level, and at the Meso level, partners
from the institution are involved like the faculty and the support staff. Simon and Timothy (2018)
stated that the business intelligence imperative to optimize processes to build better Meso levels
of analytics (ie. academic analytics). Meso-level analytics operate at institutional level. To the
extent that educational institutions share common business processes to sectors already benefiting
from business intelligence, they can be seen as a new business intelligence market sector, who can

10

GSJ© 2022
www.globalscientificjournal.com
GSJ: Volume 10, Issue 4, April 2022
ISSN 2320-9186 2310

usefully appropriate tools to integrate data silos in enterprise warehouse, optimize workflows,
generate dashboards and unstructured data.

3. Micro-Level: Might be the most popular level in learning analytics. It operates at the
interpretation and tracking of individual/learner data. At this level, student success is strongly
related where data are collected, analyzed, and translated to improve learning and increase the
success of students. Micro-level analytics support the tracking and interpretation of process-level
data for individual learners. This data is for primary interest to learners themselves, and those
responsible for their success.

According to Simon and Timothy (2018), the breadth and depth at the Macro and Meso levels add
power to micro-analytics. Aggregation of millions of learners' interaction data creates a solid
meso and macro levels. Therefore, effective learning analytics demands mutual
enrichments between the three layers of analytics.

The three layers of Analytics

MACRO

Region/state/national/international;

MESO

Institution-wide

MICRO

Individual user actions

Source: Simon and Timothy (2018)

11

GSJ© 2022
www.globalscientificjournal.com
GSJ: Volume 10, Issue 4, April 2022
ISSN 2320-9186 2311

Conclusion

Learning analytics, the analysis and representation of data about learners in order to improve
learning, is a new lens through which teachers can understand education. Learning analytics offers
new routes for teachers to understand their students and hence, make effective use of their limited
resources. Learning analytics helps to predict learner’s performance, provide learners with
personalized eLearning experience, increased learner’s retention rates, helps to improve future
eLearning courses and boost in cost efficiency.

Learning analytics helps provide educators with feedback on students learning activities and
performance. Learning analytics tool led to the enhancement of data visualization, user interface
and supported feedback types. Evaluation of the improved tools allow us to see how the
improvements affected the user’s perceived value of the tools.

Learning analytics in many respects, having ability to change the world of eLearning whether in
educational institutions or in corporate training. Learning analytics are web-based measurements
and reporting about student learning that is intended to help teachers improve the knowledge and
skill acquisition of their students. This maximizes student learning potential while enhancing
teaching and delivery methods. Though its application to education is relatively new, scientific
disciplines have been using it for over forty years.

Suggestions

1. Educational institutions need to develop relevant curriculum. They would be required to

invest in local research and develop locally relevant solution to various problems.
2. Investments in digital teaching and learning materials may need to be complemented by
investment in training for teachers if such content is to be used successfully across an
education system.

References

Alhubaitu, A., Alkhazim, M., (2014). Medical colleges in Saudi Arabia: Can we predict graduate?
Journal of Higher Education Studies, 4(3), 1-8.
Alshammari, I.A., Aldhafiri, M.D., & Alshammari, Z., (2013). A Meta-Analysis of Educational
Data Mining on Improvements in Learning Outcomes. Journal of College Student, 47(2),
326-333.

12

GSJ© 2022
www.globalscientificjournal.com
GSJ: Volume 10, Issue 4, April 2022
ISSN 2320-9186 2312

Andrew, K., Barbara, M., & Marie, B. (2018). Analytics goes to school: A collaborative approach
to improving Education. Taylor & Francis group. New York & London.
Armayor, G.M., & Leonard, S.T., (2000). Graphics Strategies for Analyzing & Interpreting
Curricular Mapping Data. American Journal of Pharmaceutical Education, 74(5), 1-10.
Bichsel, J. (2013). State of E-Learning in higher: An eye towards growth-Educause. Retrieved
from https//www.net.educause.edu>pdf> ERS1304.
Brown, M. (2013). Premise of learning analytics for educational context: through concept…
Retrieved from https//www.enformatik.ankara.edu.tr>files>2014/10.
Dede, C., Ho, A & Mitros, P., (2016). Big data analytics in higher education: promise and pitfall.
Retrieved from https//www.er.educause.edu>articles>2016.
Dicerbo, K.E., (2014). Game-based assessment of persistence. Journal of Educational Technology
and Society, 17(1), 17-28.
Dietz-Uhler, B., & Hurn, J.E., (2013). Using learning analytics to predict and improve student
success. Journal of Interactive Online Learning, 12(1), 17-26.
Dunn, K.E., Airola, D.T., Lo, W., & Garrison, M., (2013). Becoming data-driven: Exploring
teacher efficacy and concerns related to data driven decision making. Journal of
Experimental Education, 81 (1), 222-241.
Elias, T. (2013). Learning analytics methods, benefits, and challenges in higher education.
Retrieved from https//olj.onlinelearningconsortium.org>…
Gulbahar, Y. & Ilgaz, H. (2014). Premise of learning analytics for educational context: through
concept to practice. Retrieved from https//www.enformatik.ankara.edu.tr>files>2014/10.
Heath, J., & Leinonen, E., (2016). Using learning analytics to enhance the student experience. IGI
Global, 2016.
Jantawan, B., & Tsai, C., (2013). The application of data mining to build classification model for
predicting graduate employment. International Journal of Computer Science and
Information Security, 11(10), 1-7.
Long, P. & Siemens, G. (2013). Big data and learning analytics in higher education: Current…
Retrieved from https//www.books.google.com.ng>books.
Pappas, C., (2014). 5 Reasons why learning analytics are important for e-learning.
https//www.elearningindustry.com>5-reasons.
Philips, R. Moar, D. Cumming-Potvin, W. Roberts, P. Herrington, J. Preston, G. & Moore, E.
(2011). E-learning. Retrieved from https//www.davidtjones.wordpress.com>page.
Siemens, G. (2013). “Learning and knowledge analytics”. Journal of Educational technology and
society. 15(3), 1-2.
Siemens, G., & Gasevic, D., (2012). Special issue on learning and knowledge analytics.
Educational Technology & Society. 15(3), 1-163.

13

GSJ© 2022
www.globalscientificjournal.com
 GSJ: Volume 10, Issue 4, April 2022
ISSN 2320-9186 2313

Siemens, G., Dawson, S., & Lynch, G., (2013). Improving the quality and productivity of
higher…- Semantic scholar. Retrieved from https//pdfs.semanticscholar.org>…
Simon, B.S., & Timothy, A.M., (2018). Architecting for learning analytics: Innovating for
sustainable impact. https//www.er.educause.edu>articles>archite…

14

GSJ© 2022
www.globalscientificjournal.com
View publication stats